Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to roles or titles related to authority and production in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    names and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.44
     AssemblyTitle
    -0.40
     كورة
    -0.40
    didSet
    -0.39
     strict
    -0.38
    httphttps
    -0.37
    Voltaje
    -0.36
     estric
    -0.36
    المشاركات
    -0.35
     domestiques
    -0.35
    POSITIVE LOGITS
    帖最后由
    0.54
    HasForeignKey
    0.52
    
    0.49
     Professor
    0.49
     Rabbi
    0.49
     Mr
    0.48
    Parcelize
    0.48
     Mayor
    0.47
     John
    0.46
    SharedCtor
    0.46
    Act Density 0.053%

    No Known Activations